Comparer des méthodes

	Analyse de sentiments multilingue	Plongements de phrases
Domaine	Apprentissage profond	Apprentissage profond
Famille	Machine learning	Machine learning
Année d'origine	2004–2020	2015–2019
Auteur d'origine	Pang, B. & Lee, L. (early sentiment analysis); cross-lingual extension via mBERT/XLM-R community (2019–2020)	Kiros et al. (Skip-Thought, 2015); Reimers & Gurevych (Sentence-BERT, 2019)
Type	Supervised classification / fine-tuned LM	Representation learning / embedding
Source fondatrice	Conneau, A., Khandelwal, K., Goyal, N., Chaudhary, V., Wenzek, G., Guzman, F., Grave, E., Ott, M., Zettlemoyer, L., & Stoyanov, V. (2020). Unsupervised Cross-lingual Representation Learning at Scale. Proceedings of ACL 2020, 8440–8451.	Reimers, N., & Gurevych, I. (2019). Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP), 3980–3990.
Alias	cross-lingual sentiment analysis, multilingual opinion mining, multilingual sentiment classification, MSA	sentence vectors, sentence representations, SBERT, semantic sentence encoding
Apparentées	5	4
Résumé	Multilingual Sentiment Analysis (MSA) applies deep learning — most commonly a fine-tuned multilingual language model such as mBERT or XLM-RoBERTa — to classify the sentiment polarity (positive, negative, neutral) of text written in two or more languages, enabling opinion mining across language boundaries without building separate models per language.	Sentence Embeddings convert a sentence or short text into a single fixed-length dense vector that captures its semantic meaning. These vectors allow downstream tasks — semantic similarity, clustering, retrieval, and classification — to operate on numerical representations instead of raw text, making them one of the most versatile building blocks in modern NLP pipelines.